readCsvFiles.py

#!/usr/bin/python3

import os

import numpy as np
from pandas.io.parsers import read_csv
from sklearn.utils import shuffle


FTRAIN = 'datasets/training.csv'
FTEST = 'datasets/test.csv'


def load(test=False, cols=None):
    """Loads data from FTEST if *test* is True, otherwise from FTRAIN.
    Pass a list of *cols* if you're only interested in a subset of the
    target columns.
    """
    fname = FTEST if test else FTRAIN
    df = read_csv(os.path.expanduser(fname))  # load pandas dataframe

    # The Image column has pixel values separated by space; convert
    # the values to numpy arrays:
    df['Image'] = df['Image'].apply(lambda im: np.fromstring(im, sep=' '))

    if cols:  # get a subset of columns
        df = df[list(cols) + ['Image']]

    print(df.count())  # prints the number of values for each column
    df = df.dropna()  # drop all rows that have missing values in them

    X = np.vstack(df['Image'].values) / 255.  # scale pixel values to [0, 1]
    X = X.astype(np.float32) # Copy of the array, cast to a specified type.

    if not test:  # only FTRAIN has any target columns
        y = df[df.columns[:-1]].values
        y = (y - 48) / 48  # scale target coordinates to [-1, 1]
        X, y = shuffle(X, y, random_state=42)  # shuffle train data, random_state corresponding to the seed
        y = y.astype(np.float32) # Copy of the array, cast to a specified type.
    else:
        y = None

    return X, y